This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Invariant Descriptors for 3D Object Recognition and Pose
October 1991 (vol. 13 no. 10)
pp. 971-991

Invariant descriptors are shape descriptors that are unaffected by object pose, by perspective projection, or by the intrinsic parameters of the camera. These descriptors can be constructed using the methods of invariant theory, which are briefly surveyed. A range of applications of invariant descriptors in 3D model-based vision is demonstrated. First, a model-based vision system that recognizes curved plane objects irrespective of their pose is demonstrated. Curves are not reduced to polyhedral approximations but are handled as objects in their own right. Models are generated directly from image data. Once objects have been recognized, their pose can be computed. Invariant descriptors for 3D objects with plane faces are described. All these ideas are demonstrated using images of real scenes. The stability of a range of invariant descriptors to measurement error is treated in detail.

[1] S. S. Abhyankar, "Invariant theory and the enumerative combinatorics of Young tableaux," inProc. First DARPA-ESPRIT Joint Workshop Applications Invariance Comput. Vision, 1991.
[2] V.I. Arnold, "Geometrical methods in the study of ordinary differential equations," inGrundlehren der Mathematische Wissenschaft. Berlin: Springer-Verlag, 1990.
[3] H. Asada and M. Brady, "The curvature primal sketch," inProc. IEEE Workshop Comput. Vision: Representation Contr., 1984.
[4] E.B. Barrett, P.M. Payton, N.N. Haag, and M. H. Brill, "General methods for determining projective invariants in imagery,"Comput. Vision Graphics Image Proc., Jan. 1991.
[5] W. Boothby,An Introduction to Differentiable Manifolds and Riemannian Geometry. New York: Academic, 1986.
[6] R. A. Brooks, "Model-based three-dimensional interpretations of two dimensional images,"IEEE Trans. Patt. Anal. Machine Intell., vol. 5, no. 2, p. 140, 1983.
[7] J. F. Canny, "Finding lines and edges in images," Artificial Intell. Lab., Massachusetts Inst. Technol., Tech. Rep. TM-720, 1983.
[8] M. Dhome, J. T. Lapreste, G. Rives, and M. Richetin, "Spatial localization of modeled objects of revolution in monocular perspective vision," inProc. ECCVI, 1989.
[9] L. E. Dickson,Algebraic invariants.New York: Wiley, 1913.
[10] J. Dieudonnéand J. B. Carrell,Invariant Theory Old and New.New York: Academic, 1971.
[11] R. O. Duda and P. E. Hart,Pattern Classification and Scene Analysis.New York: Wiley, 1973.
[12] G. J. Ettinger, "Large hierarchical object recognition using libraries of parameterized model sub-parts,"Patt. Recog., pp. 32-41, 1988.
[13] D.A. Forsyth, J.L. Mundy, A. Zisserman, and C. M. Brown, "Projectively invariant representations using implicit algebraic curves," inProc. 1st Europ. Conf Comput. vision, Springer Verlag Lecture Notes in Computer Science, 1990.
[14] D.A. Forsyth, J.L. Mundy, A. Zisserman, and C. M. Brown, "Applications of invariant theory in computer vision," inProc. Int. Workshop Integrating Symbolic Numerical Comput., (Saratoga Springs), 1990.
[15] D.A. Forsyth, J. L. Mundy, and A. Zisserman, "Transformational invariance-a primer," inBritish Machine Vision Assoc. Conf. Proc., 1990.
[16] D.A. Forsyth, J. L. Mundy, A. Zisserman, and C. A. Rothwell, "Invariant descriptors for 3D object recognition and pose," inProc. First DARPA-ESPRIT Joint Workshop Applications Invariance Comput. Vision, 1991.
[17] S. Ganapathy, "Decomposition of transformation matrices for robot vision," inProc. Int. Conf. Robotics Automat., 1984.
[18] J. H. Grace, and A. Young,The Algebra of Invariants. Cambridge, UK: Cambridge University Press, 1903.
[19] W. E. L. Grimson and T. Lozano-Perez, "Search and sensing strategies for recognition and localization of two and three dimensional objects," inProc. 3rd Int. Symp. Robotics Research, MIT Press, 1985.
[20] R. Hartshome,Foundations of Projective Geometry.Benjamin, 1967.
[21] D. P. Huttenlocher and S. Ullman, "Recognizing solid objects by alignment," inProc. DARPA Image Understanding Workshop, 1988, p. 1114.
[22] I. Ikeuchi and T. Kanade, "Modeling sensors and applying sensor model to automatic generation of object recognition program," inProc. DARPA Image Understanding Workshop, 1988, p. 697.
[23] K. Kanatani, Group Theoretical Methods in Image Understanding, New York: Springer, 1990.
[24] D. Kapur and J.L. Mundy, "Fitting affine invariant conics to curves," inProc. First DARPA-ESPRIT Joint Workshop Applications Invariance Comput. Vision, 1991.
[25] Y. Lamdan, J. T. Schwartz, and H. J. Wolfson, "Object recognition by affine invariant matching," inProc. CVPR 88, 1988.
[26] E. P. Lane,A treatise on Projective Differential Geometry. Chicago: University of Chicago Press, 1941.
[27] S. Linnainmaa, D. Harwood, and L. S. Davis, "Pose determination for a three dimensional object using triangle pairs,"IEEE Trans. Patt. Anal. Machine Intell., vol. 10, no. 5, p. 634, 1988.
[28] D. Lowe, Perceptual Organization And Visual Recognition. Boston: Kluwer, 1985.
[29] S. Masciangelo, "3-D cues from a single view: Detection of elliptical arcs and model-based perspective backprojection," inProc. BMVC 90,(Oxford), 1990.
[30] S. J. Maybank, "The projection of two non-coplanar tonics," inProc. First DARPA-ESPRIT Joint Workshop Applications of Invariance Comput. Vision, 1991.
[31] F. H. Moffit, and E. Mikhail,Photogrammetry. New York: Harper and Row, 1990.
[32] R. Mohr and L. Morin, "Geometric solutions to some 3D vision problems," inProc. First DARPA-ESPRIT Joint Workshop Applications Invariance Comput. Vision, 1991.
[33] A. P. Morgan,Solving Polynomial Systems Using Continuation for Scientific and Engineering Problems.Englewood Cliffs, NJ: Prentice-Hall, 1987.
[34] L. Nielsen, "Automated guidance of vehicles using vision and projectively invariant marking,"Automatica, vol. 24, no. 2, pp. 135-148.
[35] L. Nielsen and G. Sparr, "Projective area-invariants as an extension of the cross-ratio," inProc. 6th Scandinavian Conf. Image Analy., (Oulu), 1989, pp. 969-986.
[36] P. J. Olver,The Application of Lie Groups to Differential Equations.New York: Springer Verlag, 1986.
[37] A. Pentland, "Automatic extraction of deformable part models,"Int. J. Comput. Vision, vol. 4, pp. 107-126, 1990.
[38] J. Ponce and D. J. Kriegman, "On recognizing and positioning curved 3D objects from image contours," inProc. DARPA Image Understanding Workshop, Palo Alto, CA, 1989, pp. 461-470.
[39] J. Ponce, A. Hoogs, and D. J. Kreigman, "On using CAD models to compute the pose of curved 3D objects," inProc. First DARPA-ESPRIT Joint Workshop Applications Invariance Comput. Vision, 1991.
[40] J. Porrill, "Fitting ellipses and predicting confidence envelopes using a bias corrected Kalman filter," inProc. 5th Alvey Vision Conf., 1989.
[41] C. A. Rothwell, A. Zisserman, C.I. Marinos, D.A. Forsyth, and J.L. Mundy, "Relative motion and pose from arbitrary plane curves,"Image Vision Computing, 1991.
[42] G. Salmon,A treatise on the Higher Plane Curves(3rd ed.), 1879.
[43] G. Salmon,Higher Algebra. Chelsea, 1885.
[44] C. E. Springer,Geometry and Analysis of Projective Spaces. San Francisco: W. H. Freeman, 1964.
[45] D. Thompson and J. Mundy, "Three dimensional model matching from an unconstrained viewpoint,"Proc. Int. Conf. Robotics Automation, 1987, pp. 208-220.
[46] R. Y. Tsai, "An efficient and accurate camera calibration technique for 3D machine vision,"IEEE J. Robotics Automat., vol. RA-3, no. 4, 1987.
[47] H. W. Turnbull,Determinants, Matrices and Invariants.Glasgow: Blackie and Son, 1928.
[48] Van Gool, L. Wagemans, J. Vandeneende, and A. Osterlinck, "Similarity extraction and modeling," inProc. ICCV 3, 1990.
[49] I. Weiss, "Projective invariants of shapes," inProc. DARPA IU Workshop, 1989, pp. 1125-1134.
[50] H. Weyl,The Classical Groups and Their Invariants 2nd ed.Princeton, NJ: Princeton University Press, 1946.

Index Terms:
invariant descriptors; pose-invariant recognition; perspective projection invariance; 3D object recognition; 3D model-based vision; curved plane objects; computerised pattern recognition; computerised picture processing
Citation:
D. Forsyth, J.L. Mundy, A. Zisserman, C. Coelho, A. Heller, C. Rothwell, "Invariant Descriptors for 3D Object Recognition and Pose," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, no. 10, pp. 971-991, Oct. 1991, doi:10.1109/34.99233
Usage of this product signifies your acceptance of the Terms of Use.